Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuine behavioral context on top: default ordering is newest-change-first unless sorted, each row reports whether a published version exists, and a draft cannot be sent. It stops short of describing pagination behavior or the default page size of 25.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the resource definition and default ordering before the routing advice, and almost every sentence carries information. Minor redundancy: 'which is what a send resolves to' and 'which version number is the published one' circle the same published-version concept twice.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must convey what comes back; it covers the published-version flag but not the item shape, whether a next cursor is returned, or how limit interacts with the total. For a five-parameter paginated list tool this leaves real gaps an agent would hit on the first call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description has to carry the load. It explains the default sort order and gives rich matching semantics for the search parameter (name, slug, description, published subject), but says nothing about limit, cursor, or what the status enum filters on — three of five parameters remain undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening names the resource precisely ('Email templates on the active connection') and even defines what a template is (stored subject and body that a send fills in and reuses), and it is clearly differentiated from getTemplate and from the search-parameter path. The one gap is that it never states the verb 'list' explicitly — it is a noun phrase that relies on the tool name to convey enumeration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names two alternatives with the conditions that select them: use the search parameter instead of paging through everything and eyeballing names, and use getTemplate when you need one template in detail with its published version number. That is explicit when-to-use / when-to-use-something-else guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.